INDEX

Explanations

punctuation marks, particularly commas, colons, and periods

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

fnlp/Llama-Scope-R1-Distill/0-Slimpajama-800M-OpenR1-Math-220k/L15R

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

open-r1/OpenR1-Math-220k

Features

32,768

Data Type

float32

Hook Name

blocks.15.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

cerebras/SlimPajama-627B

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.06

 advent

-0.06

_Common

-0.06

urn

-0.06

ses

-0.06

ols

-0.06

 Incontri

-0.06

lug

-0.06

POSITIVE LOGITS

lemn

0.07

ysz

0.06

edor

0.06

 dÃ¡n

0.06

.sig

0.06

/licenses

0.06

zyst

0.06

 etmeye

0.06

Ð½Ð¾Ð¶

0.06

 Ø§ÙĦÙħØµ

0.06

Activations Density 0.145%

punctuation marks, particularly commas, colons, and periods

No Comments

No Known Activations